Adaptive Representations for Tracking Breaking News on Twitter
|Title:||Adaptive Representations for Tracking Breaking News on Twitter||Authors:||Brigadir, Igor
|Permanent link:||http://hdl.handle.net/10197/6616||Date:||27-Aug-2014||Abstract:||Twitter is often the most up-to-date source for finding and tracking breaking news stories. Therefore, there is considerable interest in developing filters for tweet streams in order to track and summarize stories. This is a non-trivial text analytics task as tweets are short,and standard text similarity metrics often fail as stories evolve over time. In this paper we examine the effectiveness of adaptive text similarity mechanisms for tracking and summarizing breaking news stories. We evaluate the effectiveness of these mechanisms on a number of recent news events for which manually curated timelines are available. Assessments based on the ROUGE metric indicate that an adaptive similarity mechanism is best suited for tracking evolving stories on Twitter.||Type of material:||Conference Publication||Keywords:||Machine learning; Statistics; Continuous skip-gram model; Twitter||Other versions:||http://www.kdd.org/kdd2014/||Language:||en||Status of Item:||Peer reviewed||Conference Details:||NewsKDD - Workshop on Data Science for News Publishing at KDD, August 24 2014, New York, United States|
|Appears in Collections:||Insight Research Collection|
Show full item record
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.